@inproceedings{murawaki-kurohashi-2010-online,
title = "Online {J}apanese Unknown Morpheme Detection using Orthographic Variation",
author = "Murawaki, Yugo and
Kurohashi, Sadao",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}`10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L10-1111/",
abstract = "To solve the unknown morpheme problem in Japanese morphological analysis, we previously proposed a novel framework of online unknown morpheme acquisition and its implementation. This framework poses a previously unexplored problem, online unknown morpheme detection. Online unknown morpheme detection is a task of finding morphemes in each sentence that are not listed in a given lexicon. Unlike in English, it is a non-trivial task because Japanese does not delimit words by white space. We first present a baseline method that simply uses the output of the morphological analyzer. We then show that it fails to detect some unknown morphemes because they are over-segmented into shorter registered morphemes. To cope with this problem, we present a simple solution, the use of orthographic variation of Japanese. Under the assumption that orthographic variants behave similarly, each over-segmentation candidate is checked against its counterparts. Experiments show that the proposed method improves the recall of detection and contributes to improving unknown morpheme acquisition."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="murawaki-kurohashi-2010-online">
<titleInfo>
<title>Online Japanese Unknown Morpheme Detection using Orthographic Variation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yugo</namePart>
<namePart type="family">Murawaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC‘10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To solve the unknown morpheme problem in Japanese morphological analysis, we previously proposed a novel framework of online unknown morpheme acquisition and its implementation. This framework poses a previously unexplored problem, online unknown morpheme detection. Online unknown morpheme detection is a task of finding morphemes in each sentence that are not listed in a given lexicon. Unlike in English, it is a non-trivial task because Japanese does not delimit words by white space. We first present a baseline method that simply uses the output of the morphological analyzer. We then show that it fails to detect some unknown morphemes because they are over-segmented into shorter registered morphemes. To cope with this problem, we present a simple solution, the use of orthographic variation of Japanese. Under the assumption that orthographic variants behave similarly, each over-segmentation candidate is checked against its counterparts. Experiments show that the proposed method improves the recall of detection and contributes to improving unknown morpheme acquisition.</abstract>
<identifier type="citekey">murawaki-kurohashi-2010-online</identifier>
<location>
<url>https://aclanthology.org/L10-1111/</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Online Japanese Unknown Morpheme Detection using Orthographic Variation
%A Murawaki, Yugo
%A Kurohashi, Sadao
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC‘10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F murawaki-kurohashi-2010-online
%X To solve the unknown morpheme problem in Japanese morphological analysis, we previously proposed a novel framework of online unknown morpheme acquisition and its implementation. This framework poses a previously unexplored problem, online unknown morpheme detection. Online unknown morpheme detection is a task of finding morphemes in each sentence that are not listed in a given lexicon. Unlike in English, it is a non-trivial task because Japanese does not delimit words by white space. We first present a baseline method that simply uses the output of the morphological analyzer. We then show that it fails to detect some unknown morphemes because they are over-segmented into shorter registered morphemes. To cope with this problem, we present a simple solution, the use of orthographic variation of Japanese. Under the assumption that orthographic variants behave similarly, each over-segmentation candidate is checked against its counterparts. Experiments show that the proposed method improves the recall of detection and contributes to improving unknown morpheme acquisition.
%U https://aclanthology.org/L10-1111/
Markdown (Informal)
[Online Japanese Unknown Morpheme Detection using Orthographic Variation](https://aclanthology.org/L10-1111/) (Murawaki & Kurohashi, LREC 2010)
ACL